Tacotron 2 (without wavenet)

PyTorch implementation of Natural TTS Synthesis By Conditioning Wavenet On Mel Spectrogram Predictions.

This implementation includes distributed and automatic mixed precision support and uses the LJSpeech dataset.

Distributed support relies on PyTorch's native nn.parallel primitives.

Automatic Mixed Precision support relies on NVIDIA's AMP.

Visit our website for audio samples using our published Tacotron 2 and WaveGlow models.

Pre-requisites

1. NVIDIA GPU + CUDA cuDNN

Setup

1. Download and extract the LJ Speech dataset
2. Clone this repo: git clone https://github.com/NVIDIA/tacotron2.git
3. CD into this repo: cd tacotron2
4. Initialize submodule: git submodule init; git submodule update
5. Prepare DATASET directory
   • Prepare train.csv.txt and val.csv.txt files
   • Change training_files and validation_files in hparams.py to the above two files respectively
   • Make necessary modifications to files_to_list to retrieve 'mel_file_path' and 'text' in utils/dataset.py
6. Install PyTorch 1.0
7. Install python requirements or build docker image
   • Install python requirements: pip install -r requirements.txt

Training

1. python train.py --output_directory=outdir --log_directory=logdir
2. (OPTIONAL) tensorboard --logdir=outdir/logdir

Training using a pre-trained model

Training using a pre-trained model can lead to faster convergence
By default, the dataset dependent text embedding layers are ignored

1. Download our published Tacotron 2 model
2. python train.py --output_directory=outdir --log_directory=logdir -c tacotron2_statedict.pt --warm_start

Multi-GPU (distributed) Training

1. python train.py --output_directory=outdir --log_directory=logdir --hparams=distributed_run=True

Automatic Mixed Precision Training

1. python train.py --output_directory=outdir --log_directory=logdir --hparams=fp16_run=True

Inference demo

1. Download our published Tacotron 2 model
2. Download our published WaveGlow model
3. jupyter notebook --ip=127.0.0.1 --port=31337
4. Load inference.ipynb

N.b. When performing Mel-Spectrogram to Audio synthesis, make sure Tacotron 2 and the Mel decoder were trained on the same mel-spectrogram representation.

Related repos

WaveGlow Faster than real time Flow-based Generative Network for Speech Synthesis

nv-wavenet Faster than real time WaveNet.

Acknowledgements

This implementation uses code from the following repos: Keith Ito, Prem Seetharaman as described in our code.

We are inspired by Ryuchi Yamamoto's Tacotron PyTorch implementation.

We are thankful to the Tacotron 2 paper authors, specially Jonathan Shen, Yuxuan Wang and Zongheng Yang.